© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154306
    Prev
    Next
    INDEX
    Explanations

    engineering concepts and structures

    np_acts-logits-general · gemini-2.5-flash-lite

    describes a or b

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    圣
    0.54
    疯狂
    0.52
    ват
    0.51
    旋转
    0.49
    缭
    0.47
    预计
    0.46
    чим
    0.46
    标志
    0.45
    吝
    0.45
    价
    0.45
    POSITIVE LOGITS
     ingeniería
    0.53
     locomotive
    0.53
     intelectual
    0.52
     engineering
    0.51
    ducers
    0.49
     antenna
    0.48
     aparelho
    0.48
     vostre
    0.47
     aparece
    0.47
     locomotor
    0.47
    Activations Density 0.000%

    No Known Activations